INDEX

Explanations

words and classes related to programming constructs and types in a large codebase

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ſelves

-0.95

 itſelf

-0.86

 myſelf

-0.85

ſelf

-0.83

 ſtate

-0.83

 pleaſure

-0.82

 fevere

-0.80

 Majefty

-0.79

 ſever

-0.79

 houſe

-0.79

POSITIVE LOGITS

[]

0.67

aux

0.56

itu

0.54

inex

0.54

0.52

 Nature

0.51

 nature

0.51

ós

0.50

Gön

0.49

Activations Density 0.308%

words and classes related to programming constructs and types in a large codebase

No Comments

No Known Activations